Robustness of convergence in finite time for linear programming neural networks
Mauro Di Marco, Mauro Forti, Massimo Grazzini · International Journal of Circuit Theory and Applications · 2006
Abstract A recent work has introduced a class of neural networks for solving linear programming problems, where all trajectories converge toward the global optimal solution in finite time. In this paper, it is shown that global convergence in finite time is robust with respect to tolerances in the electronic implementation, and an estimate of the allowed perturbations preserving convergence is obtained. Copyright © 2006 John Wiley & Sons, Ltd.